Create app.py

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_ID = "melihemin/qwen2.5-0.5b-text2sql-full"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def text_to_sql(question):
+    prompt = f"""### Question:
+{question}
+
+### SQL:
+"""
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=128,
+        do_sample=False
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+demo = gr.Interface(
+    fn=text_to_sql,
+    inputs=gr.Textbox(
+        lines=4,
+        placeholder="How many heads of the departments are older than 56?"
+    ),
+    outputs="text",
+    title="Text to SQL Demo",
+    description="Qwen2.5-0.5B fine-tuned for Text-to-SQL"
+)
+
+demo.launch()